Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. MLP Out - 16k
    5. 6-GEMMASCOPE-MLP-16K
    6. 151
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'a' and variations in its capitalization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.69
    yntaxException
    -0.69
    a
    -0.67
    HomeAsUpEnabled
    -0.65
    <?
    -0.65
     <>",
    -0.64
    A
    -0.63
    WebControls
    -0.62
    хьтан
    -0.62
     wijk
    -0.62
    POSITIVE LOGITS
     createSlice
    0.57
     CLERK
    0.49
     Leib
    0.48
     Lieb
    0.47
     MACHINE
    0.46
    èt
    0.46
     ml
    0.46
    erse
    0.45
    ml
    0.44
     getField
    0.44
    Activations Density 0.481%

    No Known Activations